Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/wordflowlab/novel-writerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/wordflowlab/novel-writer/plan)<a href="https://agentmods.dev/commands/wordflowlab/novel-writer/plan"><img src="https://agentmods.dev/badge/commands/wordflowlab/novel-writer/plan.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.01408 |
| Opus 5 | $0.00004 | $0.00704 |
| Sonnet 5 | $0.00002 | $0.00282 |
| Haiku 4.5 | $0.00001 | $0.00141 |
Grade A, and why
plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
基于澄清后的故事规格，制定具体的创作技术方案。
用户输入（技术选择和偏好）： $ARGUMENTS
目标
将"要创造什么"（规格）转化为"如何创造"（计划）。这是从需求到实现的关键转换。
执行步骤
1. 加载前置文档
运行 {SCRIPT} 检查并加载：
- 宪法文件：
memory/novel-constitution.md - 规格文件：
stories/*/specification.md - 澄清记录（如果已运行
/clarify）
验证规格中的 [需要澄清] 标记：
- 如果存在未澄清的关键决策，提示先运行
/clarify - 或接受用户明确指示跳过
2. 制定创作计划
创建 stories/*/creative-plan.md，包含以下内容：
2.1 写作方法选择
基于规格分析，选择最适合的写作方法：
- 三幕结构：适合线性叙事、明确起承转合
- 英雄之旅：适合成长型、冒险类故事
- 七点结构：适合悬念、反转类故事
- 故事圈：适合角色驱动、心理深度
- 混合方法：主线+支线使用不同方法
记录选择理由和应用方式。
2.2 章节架构设计
## 章节架构
### 总体规划
- 总章数：[基于目标字数和章节长度]
- 章节长度：[2000-3000字/章]
- 分卷安排：[如适用]
### 结构映射
[根据选定方法，映射关键节点到具体章节]
### 节奏设计
- 开篇钩子：第[X]章
- 第一个高潮：第[X]章
- 中点转折：第[X]章
- 最大危机：第[X]章
- 最终高潮：第[X]章
2.3 人物体系设计
## 人物体系
### 主角设计
- 初始状态：[起点]
- 成长弧线：[变化轨迹]
- 核心冲突：[内在vs外在]
- 关键转变点：[具体章节]
### 配角功能
[每个重要配角的功能定位和出场计划]
### 关系网络
[人物关系图和演变计划]
2.4 世界观构建
## 世界观体系
### 核心设定
- 世界规则：[物理/魔法/科技规则]
- 社会结构：[政治/经济/文化]
- 历史背景：[重要历史事件]
### 设定展开计划
- 第一层（开篇）：[基础设定]
- 第二层（发展）：[深入设定]
- 第三层（高潮）：[核心秘密]
2.5 情节技术设计
## 情节技术
### 冲突升级路径
1. 初级冲突：[个人层面]
2. 中级冲突：[团体层面]
3. 高级冲突：[世界层面]
### 悬念设置
- 主悬念：[贯穿全文]
- 章节悬念：[每章钩子]
- 支线悬念：[丰富层次]
### 伏笔布局
[伏笔清单和回收计划]
2.6 叙事技术选择
## 叙事技术
### POV设计
- 视角类型：[第一/第三人称]
- 视角限制：[全知/限定]
- 多视角安排：[如适用]
### 时间线设计
- 主线时间：[线性/非线性]
- 回忆穿插：[使用策略]
- 平行叙事：[如适用]
### 叙事节奏
- 快节奏段落：[动作/冲突]
- 慢节奏段落：[情感/描写]
- 节奏变化：[张弛规律]
3. 技术决策记录
记录所有重要的技术决策：
- 决策：选择了什么
- 理由：为什么选择
- 风险：可能的问题
- 备案：替代方案
4. 质量保证计划
## 质量保证
### 自检清单
- [ ] 逻辑一致性检查点
- [ ] 人物行为合理性
- [ ] 世界观自洽性
- [ ] 节奏流畅性
### 验证节点
- 每5章：小循环验证
- 每卷：大循环验证
- 完稿：全面验证
5. 风险管理
识别并制定应对策略：
- 创作风险：灵感、逻辑、节奏
- 技术风险：复杂度、一致性
- 时间风险：进度、质量平衡
6. 输出和验证
- 保存计划到
stories/*/creative-plan.md - 验证计划符合宪法原则
- 验证计划满足规格需求
- 提示下一步：运行
/tasks生成任务
与其他命令的关系
- 输入：来自
/specify的规格 +/clarify的澄清 - 输出：为
/tasks提供任务生成依据 - 验证：被
/analyze用于检查实现符合度
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 202 lines · 8 tokens per session scan A 1567e0f8d164
plan is a command published in the GitHub repository wordflowlab/novel-writer (940 stars, last pushed 10mo ago), licensed MIT. It adds 8 tokens to every session and 1,408 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.